Using AI to Visualize & Analyze Human Heartbeat Data

~ newton

This entire project is an extension of work I did as a Research Experience for Teachers intern at Rice University in 2018 and 2019.

Bringing AI/ML and HPC to High School Science Teachers Using Jupyter Notebooks – TACCster 2026

~ newton

James Newland, Kelsey Beavers, Lena Duplechin Seymour, Elaine Anita de Melo Gomes Soares
Texas Advanced Computing Center, University of Texas at Austin

Abstract

Many scientific disciplines have become driven by data science methodology, requiring both statistical thinking and computation. Teachers can learn about the use of HPC, which can be transferred to classroom activities through Python and Jupyter notebooks. The use of Jupyter notebooks as computational essays in teacher professional development allows educators to experiment with and learn about HPC, data science, and machine learning algorithms using Python in various science contexts. Cloud-based platforms exist that allow access to HPC resources like multi-core processing and GPU usage for AI/ML contexts. The Jupyter notebook environment allows narrative and code to exist side by side to introduce learners to HPC computing concepts while also running code blocks that can run models or data visualizations. For those who are new to using computer programming, the notebooks can be written using research-backed computer science scaffolding pedagogy like worked examples, sub-task labeling, and minimally working programs. The use of Jupyter notebooks in educational contexts emulates HPC professional development techniques used with students and early-career scientists, like training sessions held at the Texas Advanced Computing Center (TACC). By using scaffolded techniques for educators built on successful professional learning designed for HPC users, teachers can bring authentic data science and machine learning concepts into their own classrooms. Specific examples will be explored related to biology, astronomy, and usage of LLMs in a computer science education context. The authors will explore HPC concepts like parallel data processing, machine learning applications, and large data structure usage.

Background

The TACC life sciences team has been providing professional learning for biologists for a while. The Expanding Pathways in Computing team has been doing the same for teachers. This project is an attempt to create teacher professional development content by scaffolding the ML for Life Sciences @ TACC training designed for practicing scientists. The use of high-performance computing (HPC) in educational contexts will require creativity. In addition to the AI/ML biology materials, this poster shows the use of a Google Colab notebook as a computational essay for use in an astronomy education context. The 2026 MORIA NITARP team of educators were tasked with exploring the active galactic nuclei (AGN) catalog of the Euclid spacecraft through comparison with the WISE AGN catalog. The use of Google Colab as a proxy for HPC use.

Poster

TACCster 2026 AI/ML & HPC for Science Teaching Poster

Links

References Cited

  • 1Allen, W. J., Beavers, K. M., Ferlanti, E., Concia, L., Urrutia, J., Lima, E. A. B. F., Fonner, J. M., Zuo, F., Duplechin Seymour, H. E., Kahn, A. B., Stubbs, J., Jamthe, A., Baker, S. N., Khan, T., & Carson, J. P. (2025). A Model for Teaching Machine Learning, Deep Learning, and Research Computing to Domain Scientists on HPC Resources. Proceedings of the SC ’25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, 401–408. https://doi.org/10.1145/3731599.3767380
  • 2Moore, K. S., Rabinowitz, G., Ali, S., Weckel, M., Lee, I., Gupta, P., & Chaffee, R. (2026). Design of a science integrated secondary school AI literacy curriculum: A youth & AI expert guided design-based research approach. Computers and Education: Artificial Intelligence, 10. https://doi.org/10.1016/j.caeai.2026.100552
  • 3Newland, J. (2025). Using Data Science in High School Astronomy. ASP 2024: Astronomy Across the Spectrum, Astronomical Society of the Pacific Conference Series, 539, 147. http://arxiv.org/abs/2501.04856
  • 4Peters-Burton, E., Rich, P. J., Kitsantas, A., Stehle, S. M., & Laclede, L. (2023). High school biology teachers’ integration of computational thinking into data practices to support student investigations. Journal of Research in Science Teaching, 60(6), 1353–1384. https://doi.org/10.1002/tea.21834

Acnknowledgements

The authors acknowledge the Texas Advanced Computing Center (TACC) at The University of Texas at Austin for providing computational resources that have contributed to the development of this content. URL: http://www.tacc.utexas.edu. Use of Frontera and Vista is made possible by National Science Foundation award OAC 1818253. Content development was supported by NIH Common Fund U54 DA049110. This work is in possible in part due to the work of the NASA/IPAC Teacher Archive Research program. Funding for NITARP comes from the NASA ADP program and the NASA/Archive EPO program. URL: https://nitarp.ipac.caltech.edu/

Data Driven Amateur Astronomy

~ newton

Houston Astronomical Society December 5th, 2025

Modern astronomy research has become data-driven. Using data science techniques alongside computation allows us to interrogate data to understand astrophysical phenomena. The explosion of data sets has opened up new ways for enterprising amateur astronomers to contribute to modern astronomical research. Data can come from large-scale surveys, space-based observatories, individual scientists, or students. You can learn to select, reduce, visualize, and interpret authentic astronomical data while applying data science techniques to construct astronomy knowledge. Many free web-based tools leverage data science techniques. This talk explores how these activities bridge the gap between data science and astronomy, enabling amateurs to learn about both simultaneously.

The content of this talk can be cited as: Newland, J. (2025). Using Data Science in High School Astronomy. ASP 2024: Astronomy Across the Spectrum, 539, 147. http://arxiv.org/abs/2501.04856

The Google Colab (Jupyter Notebook) developed by Sara Kannan and me can be found here. Note that the actual catalog we created is not publicly available, so this notebook requires an existing catalog for SED creation.

If you are interested in data-driven astronomy learning, check out the page below from a talk given at the first-ever Data Science Education in K12 Conference. Even though the materials shared were designed for teaching high school astronomy, enterprising amateur astronomers can still pick up some cool tricks.

Integrating Data Science Pedagogy into Astronomy Courses